Sota Kawakami
ABSTRACT
The purpose of this paper is two-fold. First, we propose two new blind image deconvolution (BID) methods by improving Ahmed's BID method [1] in 2014 that is based on techniques of low-rank matrix recovery. The first method is introducing the total variation regularization term into Ahmed's BID method for the single-input-single-output (SISO) imaging model. The second method is extending Ahmed's BID method to the single-input-multiple-output (SIMO) imaging model. The practical iterative algorithm is developed to solve the formulated BID problem in each case when we take so-called iterative singular value thresholding algorithm. In the next part, we apply the new algorithm for the SIMO case, which is more stable than the SISO case, to the problem in generating all-in-focus images. We often have such a kind of problem when we take multiple images with different focal lengths for a 3-D scene holding varying depth. We demonstrate performances of the proposed methods through simulation studies as well as real data experiments.
- Ahmed, A., Recht, B., and Romberg, J. Blind deconvolution using convex programming, IEEE Trans. Inf. Theory, vol. 60, pp.1711--1732, 2014 Google Scholar
Digital Library
- Ayers, G. R. and Dainty, J. C., Iterative blind deconvolution method and its applications, Opt. Lett., vol.13, pp.547--549, 1988Google ScholarCross Ref
- Kondur, D. and Hatzinakos, D. Blind image deconvolution, IEEE Signal Processing Mag., vol.13, pp.43--64, 1996Google ScholarCross Ref
- Sroubek, F., Cristobal, G., and Flusser, J., A unified approach to superresolution and multichannel blind deconvolution, IEEE Trans. Image Process., vol.16, pp.2322--2333, 2007 Google ScholarDigital Library
- Huangpeng, Q. Z., Zeng, X. G., Sun, Q., and Fan, J.Super-resolving blurry multiframe images through multiframe blind deblurring using ADMM, Multimedia Tools and Applications, pp.1--17, 2016. Google ScholarDigital Library
- Lee, C. and Hwang, W. Mixture of gaussian blur kernel representation for blind image restoration, IEEE Transactions on Computational Imaging, vol. PP, no. 99, pp. 1--1, 2017.Google Scholar
- Ma, T. H., Huang, T. Z., Zhao, X. L., and Lou, Y. Image deblurring with an inaccurate blur kernel using a group-based low-rank image prior, Information Sciences, vol. 408, pp. 213--233, 2017Google ScholarCross Ref
- Chambolle, A. An algorithm for total variation minimization and applications, J. Math. Imag. Vis., vol.20, pp.89--97, 2004 Google ScholarDigital Library
- Candes, E. J., Strohmer, T., and Voroninski, V. Phaselift: Exact and stable signal recovery from magnitude measurements via convex programming, Comm. Pure Appl. Math., vol.66, pp.1017--1026, 2013Google ScholarCross Ref
- Cai, J. F., Candes, E. J., and Shen, Z. A singular value thresholding algorithm for matrix completion, SIAM J. Opt., vol. 20, pp.1956--1982, 2010Google ScholarDigital Library
Index Terms
- All-in-Focus Image Generation Using Improved Blind Image Deconvolution Technique
Recommendations
An adaptive two phase blind image deconvolution algorithm for an iterative regularization model
Highlights- Proposing a model for blind image deconvolution which adopts the L 0-norm and total variation to regularize the latent image and blur ...
AbstractThis paper proposes a blind image deconvolution method which consists of two sequential phases, i.e., blur kernel estimation and image restoration. In the first phase, we adopt the L 0-norm of image gradients and total ...
Blind image deconvolution via dispersion minimization
In linear image restoration, the point spread function of the degrading system is assumed known even though this information is usually not available in real applications. As a result, both blur identification and image restoration must be performed ...
Out-of-focus Blur estimation for blind image deconvolution: using particle swarm optimization
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsThis study addresses the blind image deconvolution which uses only blurred image and less point spread function (PSF) information to restore the original image. To identify the blind image it is a very important step for restoring the image. Therefore, ...
Comments